Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/esm2_t30_150M_UR50D",
+  "_name_or_path": "facebook/esm2_t6_8M_UR50D",
   "architectures": [
     "EsmForSequenceClassification"
   ],
@@ -9,25 +9,19 @@
   "esmfold_config": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 640,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "hidden_size": 320,
   "initializer_range": 0.02,
-  "intermediate_size": 2560,
+  "intermediate_size": 1280,
   "is_folding_model": false,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_eps": 1e-05,
   "mask_token_id": 32,
   "max_position_embeddings": 1026,
   "model_type": "esm",
   "num_attention_heads": 20,
-  "num_hidden_layers": 30,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "rotary",
-  "problem_type": "regression",
+  "problem_type": "multi_label_classification",
   "token_dropout": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817378bead6ec0b3a20e40e72e27df2ba89e090c5743f909a6ec171deae00811
-size 595246640
+oid sha256:baa8b862aedecaf6669617f3456b04b9e435007f0142a00713c42b85839b81e6
+size 31375788

runs/Jul28_16-53-18_DESKTOP-M4AOP5S/events.out.tfevents.1722181999.DESKTOP-M4AOP5S.15308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717ce87c3769811709136f7fd975879bef597f33efb483b48b21d1f9d713f8ea
+size 4682

runs/Jul28_16-56-32_DESKTOP-M4AOP5S/events.out.tfevents.1722182193.DESKTOP-M4AOP5S.15308.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292395bf7ff036950308c2916e3ed55d3c3ac8e19f7e23d446fa17b7e2380bee
+size 4682

runs/Jul28_16-57-48_DESKTOP-M4AOP5S/events.out.tfevents.1722182268.DESKTOP-M4AOP5S.15308.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c26c67baca49a913ab0da9f872c9d038b7c224db58983d56f4d7aa8652710f8
+size 5063

tokenizer_config.json

@@ -45,7 +45,7 @@
   "cls_token": "<cls>",
   "eos_token": "<eos>",
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
   "tokenizer_class": "EsmTokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d24373f7936c0b9d17a25a934239c7fd92bfa122fae23690bbbce815725efa
+oid sha256:2bc7710f28812e5cf9aa4f21eaaf3b29d23d5b2d114f3540a929acde9323c200
 size 4920